maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/WebAssembly/conv-trap.ll

160 lines
6.1 KiB
LLVM
Raw Normal View History

[WebAssembly] Added default stack-only instruction mode for MC. Summary: Made it convert from register to stack based instructions, and removed the registers. Fixes to related code that was expecting register based instructions. Added the correct testing flag to all tests, depending on what the format they were expecting so far. Translated one test to stack format as example: reg-stackify-stack.ll tested: llvm-lit -v `find test -name WebAssembly` unittests/MC/* Reviewers: dschuff, sunfish Subscribers: sbc100, jgravelle-google, eraman, aheejin, llvm-commits, jfb Differential Revision: https://reviews.llvm.org/D51241 llvm-svn: 340750
2018-08-27 23:45:51 +08:00
; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -mattr=-nontrapping-fptoint | FileCheck %s
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; Test that basic conversion operations assemble as expected using
; the trapping opcodes and explicit code to suppress the trapping.
target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128"
[WebAsembly] Update default triple in test files to wasm32-unknown-unkown. Summary: The final -wasm component has been the default for some time now. Subscribers: jfb, dschuff, jgravelle-google, eraman, aheejin, JDevlieghere, sunfish, llvm-commits Differential Revision: https://reviews.llvm.org/D46342 llvm-svn: 332007
2018-05-11 01:49:11 +08:00
target triple = "wasm32-unknown-unknown"
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; CHECK-LABEL: i32_trunc_s_f32:
[WebAssembly] replaced .param/.result by .functype Summary: This makes it easier/cleaner to generate a single signature from this directive. Also: - Adds the symbol name, such that we don't depend on the location of this directive anymore. - Actually constructs the signature in the assembler, and make the assembler own it. - Refactor the use of MVT vs ValType in the streamer and assembler to require less conversions overall. - Changed 700 or so tests to use it. Reviewers: sbc100, dschuff Subscribers: jgravelle-google, eraman, aheejin, sunfish, jfb, llvm-commits Differential Revision: https://reviews.llvm.org/D54652 llvm-svn: 347228
2018-11-20 01:10:36 +08:00
; CHECK-NEXT: .functype i32_trunc_s_f32 (f32) -> (i32){{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; CHECK-NEXT: block
; CHECK-NEXT: f32.abs $push[[ABS:[0-9]+]]=, $0{{$}}
; CHECK-NEXT: f32.const $push[[LIMIT:[0-9]+]]=, 0x1p31{{$}}
; CHECK-NEXT: f32.lt $push[[LT:[0-9]+]]=, $pop[[ABS]], $pop[[LIMIT]]{{$}}
[WebAssembly] Fix fptoui lowering bounds To fully avoid trapping on wasm, fptoui needs a second check to ensure that the operand isn't below the supported range. llvm-svn: 319354
2017-11-30 04:20:11 +08:00
; CHECK-NEXT: br_if 0, $pop[[LT]]{{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; CHECK-NEXT: i32.const $push[[ALT:[0-9]+]]=, -2147483648{{$}}
; CHECK-NEXT: return $pop[[ALT]]{{$}}
[WebAssembly] Fix fptoui lowering bounds To fully avoid trapping on wasm, fptoui needs a second check to ensure that the operand isn't below the supported range. llvm-svn: 319354
2017-11-30 04:20:11 +08:00
; CHECK-NEXT: BB
; CHECK-NEXT: end_block
; CHECK-NEXT: i32.trunc_s/f32 $push[[NUM:[0-9]+]]=, $0{{$}}
; CHECK-NEXT: return $pop[[NUM]]{{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
define i32 @i32_trunc_s_f32(float %x) {
%a = fptosi float %x to i32
ret i32 %a
}
; CHECK-LABEL: i32_trunc_u_f32:
[WebAssembly] replaced .param/.result by .functype Summary: This makes it easier/cleaner to generate a single signature from this directive. Also: - Adds the symbol name, such that we don't depend on the location of this directive anymore. - Actually constructs the signature in the assembler, and make the assembler own it. - Refactor the use of MVT vs ValType in the streamer and assembler to require less conversions overall. - Changed 700 or so tests to use it. Reviewers: sbc100, dschuff Subscribers: jgravelle-google, eraman, aheejin, sunfish, jfb, llvm-commits Differential Revision: https://reviews.llvm.org/D54652 llvm-svn: 347228
2018-11-20 01:10:36 +08:00
; CHECK-NEXT: .functype i32_trunc_u_f32 (f32) -> (i32){{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; CHECK-NEXT: block
; CHECK-NEXT: f32.const $push[[LIMIT:[0-9]+]]=, 0x1p32{{$}}
; CHECK-NEXT: f32.lt $push[[LT:[0-9]+]]=, $0, $pop[[LIMIT]]{{$}}
[WebAssembly] Fix fptoui lowering bounds To fully avoid trapping on wasm, fptoui needs a second check to ensure that the operand isn't below the supported range. llvm-svn: 319354
2017-11-30 04:20:11 +08:00
; CHECK-NEXT: f32.const $push[[ZERO:[0-9]+]]=, 0x0p0{{$}}
; CHECK-NEXT: f32.ge $push[[GE:[0-9]+]]=, $0, $pop[[ZERO]]{{$}}
; CHECK-NEXT: i32.and $push[[AND:[0-9]+]]=, $pop[[LT]], $pop[[GE]]{{$}}
; CHECK-NEXT: br_if 0, $pop[[AND]]{{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; CHECK-NEXT: i32.const $push[[ALT:[0-9]+]]=, 0{{$}}
; CHECK-NEXT: return $pop[[ALT]]{{$}}
[WebAssembly] Fix fptoui lowering bounds To fully avoid trapping on wasm, fptoui needs a second check to ensure that the operand isn't below the supported range. llvm-svn: 319354
2017-11-30 04:20:11 +08:00
; CHECK-NEXT: BB
; CHECK-NEXT: end_block
; CHECK-NEXT: i32.trunc_u/f32 $push[[NUM:[0-9]+]]=, $0{{$}}
; CHECK-NEXT: return $pop[[NUM]]{{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
define i32 @i32_trunc_u_f32(float %x) {
%a = fptoui float %x to i32
ret i32 %a
}
; CHECK-LABEL: i32_trunc_s_f64:
[WebAssembly] replaced .param/.result by .functype Summary: This makes it easier/cleaner to generate a single signature from this directive. Also: - Adds the symbol name, such that we don't depend on the location of this directive anymore. - Actually constructs the signature in the assembler, and make the assembler own it. - Refactor the use of MVT vs ValType in the streamer and assembler to require less conversions overall. - Changed 700 or so tests to use it. Reviewers: sbc100, dschuff Subscribers: jgravelle-google, eraman, aheejin, sunfish, jfb, llvm-commits Differential Revision: https://reviews.llvm.org/D54652 llvm-svn: 347228
2018-11-20 01:10:36 +08:00
; CHECK-NEXT: .functype i32_trunc_s_f64 (f64) -> (i32){{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; CHECK-NEXT: block
; CHECK-NEXT: f64.abs $push[[ABS:[0-9]+]]=, $0{{$}}
; CHECK-NEXT: f64.const $push[[LIMIT:[0-9]+]]=, 0x1p31{{$}}
; CHECK-NEXT: f64.lt $push[[LT:[0-9]+]]=, $pop[[ABS]], $pop[[LIMIT]]{{$}}
[WebAssembly] Fix fptoui lowering bounds To fully avoid trapping on wasm, fptoui needs a second check to ensure that the operand isn't below the supported range. llvm-svn: 319354
2017-11-30 04:20:11 +08:00
; CHECK-NEXT: br_if 0, $pop[[LT]]{{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; CHECK-NEXT: i32.const $push[[ALT:[0-9]+]]=, -2147483648{{$}}
; CHECK-NEXT: return $pop[[ALT]]{{$}}
[WebAssembly] Fix fptoui lowering bounds To fully avoid trapping on wasm, fptoui needs a second check to ensure that the operand isn't below the supported range. llvm-svn: 319354
2017-11-30 04:20:11 +08:00
; CHECK-NEXT: BB
; CHECK-NEXT: end_block
; CHECK-NEXT: i32.trunc_s/f64 $push[[NUM:[0-9]+]]=, $0{{$}}
; CHECK-NEXT: return $pop[[NUM]]{{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
define i32 @i32_trunc_s_f64(double %x) {
%a = fptosi double %x to i32
ret i32 %a
}
; CHECK-LABEL: i32_trunc_u_f64:
[WebAssembly] replaced .param/.result by .functype Summary: This makes it easier/cleaner to generate a single signature from this directive. Also: - Adds the symbol name, such that we don't depend on the location of this directive anymore. - Actually constructs the signature in the assembler, and make the assembler own it. - Refactor the use of MVT vs ValType in the streamer and assembler to require less conversions overall. - Changed 700 or so tests to use it. Reviewers: sbc100, dschuff Subscribers: jgravelle-google, eraman, aheejin, sunfish, jfb, llvm-commits Differential Revision: https://reviews.llvm.org/D54652 llvm-svn: 347228
2018-11-20 01:10:36 +08:00
; CHECK-NEXT: .functype i32_trunc_u_f64 (f64) -> (i32){{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; CHECK-NEXT: block
; CHECK-NEXT: f64.const $push[[LIMIT:[0-9]+]]=, 0x1p32{{$}}
; CHECK-NEXT: f64.lt $push[[LT:[0-9]+]]=, $0, $pop[[LIMIT]]{{$}}
[WebAssembly] Fix fptoui lowering bounds To fully avoid trapping on wasm, fptoui needs a second check to ensure that the operand isn't below the supported range. llvm-svn: 319354
2017-11-30 04:20:11 +08:00
; CHECK-NEXT: f64.const $push[[ZERO:[0-9]+]]=, 0x0p0{{$}}
; CHECK-NEXT: f64.ge $push[[GE:[0-9]+]]=, $0, $pop[[ZERO]]{{$}}
; CHECK-NEXT: i32.and $push[[AND:[0-9]+]]=, $pop[[LT]], $pop[[GE]]{{$}}
; CHECK-NEXT: br_if 0, $pop[[AND]]{{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; CHECK-NEXT: i32.const $push[[ALT:[0-9]+]]=, 0{{$}}
; CHECK-NEXT: return $pop[[ALT]]{{$}}
[WebAssembly] Fix fptoui lowering bounds To fully avoid trapping on wasm, fptoui needs a second check to ensure that the operand isn't below the supported range. llvm-svn: 319354
2017-11-30 04:20:11 +08:00
; CHECK-NEXT: BB
; CHECK-NEXT: end_block
; CHECK-NEXT: i32.trunc_u/f64 $push[[NUM:[0-9]+]]=, $0{{$}}
; CHECK-NEXT: return $pop[[NUM]]{{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
define i32 @i32_trunc_u_f64(double %x) {
%a = fptoui double %x to i32
ret i32 %a
}
; CHECK-LABEL: i64_trunc_s_f32:
[WebAssembly] replaced .param/.result by .functype Summary: This makes it easier/cleaner to generate a single signature from this directive. Also: - Adds the symbol name, such that we don't depend on the location of this directive anymore. - Actually constructs the signature in the assembler, and make the assembler own it. - Refactor the use of MVT vs ValType in the streamer and assembler to require less conversions overall. - Changed 700 or so tests to use it. Reviewers: sbc100, dschuff Subscribers: jgravelle-google, eraman, aheejin, sunfish, jfb, llvm-commits Differential Revision: https://reviews.llvm.org/D54652 llvm-svn: 347228
2018-11-20 01:10:36 +08:00
; CHECK-NEXT: .functype i64_trunc_s_f32 (f32) -> (i64){{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; CHECK-NEXT: block
; CHECK-NEXT: f32.abs $push[[ABS:[0-9]+]]=, $0{{$}}
; CHECK-NEXT: f32.const $push[[LIMIT:[0-9]+]]=, 0x1p63{{$}}
; CHECK-NEXT: f32.lt $push[[LT:[0-9]+]]=, $pop[[ABS]], $pop[[LIMIT]]{{$}}
[WebAssembly] Fix fptoui lowering bounds To fully avoid trapping on wasm, fptoui needs a second check to ensure that the operand isn't below the supported range. llvm-svn: 319354
2017-11-30 04:20:11 +08:00
; CHECK-NEXT: br_if 0, $pop[[LT]]{{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; CHECK-NEXT: i64.const $push[[ALT:[0-9]+]]=, -9223372036854775808{{$}}
; CHECK-NEXT: return $pop[[ALT]]{{$}}
[WebAssembly] Fix fptoui lowering bounds To fully avoid trapping on wasm, fptoui needs a second check to ensure that the operand isn't below the supported range. llvm-svn: 319354
2017-11-30 04:20:11 +08:00
; CHECK-NEXT: BB
; CHECK-NEXT: end_block
; CHECK-NEXT: i64.trunc_s/f32 $push[[NUM:[0-9]+]]=, $0{{$}}
; CHECK-NEXT: return $pop[[NUM]]{{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
define i64 @i64_trunc_s_f32(float %x) {
%a = fptosi float %x to i64
ret i64 %a
}
; CHECK-LABEL: i64_trunc_u_f32:
[WebAssembly] replaced .param/.result by .functype Summary: This makes it easier/cleaner to generate a single signature from this directive. Also: - Adds the symbol name, such that we don't depend on the location of this directive anymore. - Actually constructs the signature in the assembler, and make the assembler own it. - Refactor the use of MVT vs ValType in the streamer and assembler to require less conversions overall. - Changed 700 or so tests to use it. Reviewers: sbc100, dschuff Subscribers: jgravelle-google, eraman, aheejin, sunfish, jfb, llvm-commits Differential Revision: https://reviews.llvm.org/D54652 llvm-svn: 347228
2018-11-20 01:10:36 +08:00
; CHECK-NEXT: .functype i64_trunc_u_f32 (f32) -> (i64){{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; CHECK-NEXT: block
; CHECK-NEXT: f32.const $push[[LIMIT:[0-9]+]]=, 0x1p64{{$}}
; CHECK-NEXT: f32.lt $push[[LT:[0-9]+]]=, $0, $pop[[LIMIT]]{{$}}
[WebAssembly] Fix fptoui lowering bounds To fully avoid trapping on wasm, fptoui needs a second check to ensure that the operand isn't below the supported range. llvm-svn: 319354
2017-11-30 04:20:11 +08:00
; CHECK-NEXT: f32.const $push[[ZERO:[0-9]+]]=, 0x0p0{{$}}
; CHECK-NEXT: f32.ge $push[[GE:[0-9]+]]=, $0, $pop[[ZERO]]{{$}}
; CHECK-NEXT: i32.and $push[[AND:[0-9]+]]=, $pop[[LT]], $pop[[GE]]{{$}}
; CHECK-NEXT: br_if 0, $pop[[AND]]{{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; CHECK-NEXT: i64.const $push[[ALT:[0-9]+]]=, 0{{$}}
; CHECK-NEXT: return $pop[[ALT]]{{$}}
[WebAssembly] Fix fptoui lowering bounds To fully avoid trapping on wasm, fptoui needs a second check to ensure that the operand isn't below the supported range. llvm-svn: 319354
2017-11-30 04:20:11 +08:00
; CHECK-NEXT: BB
; CHECK-NEXT: end_block
; CHECK-NEXT: i64.trunc_u/f32 $push[[NUM:[0-9]+]]=, $0{{$}}
; CHECK-NEXT: return $pop[[NUM]]{{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
define i64 @i64_trunc_u_f32(float %x) {
%a = fptoui float %x to i64
ret i64 %a
}
; CHECK-LABEL: i64_trunc_s_f64:
[WebAssembly] replaced .param/.result by .functype Summary: This makes it easier/cleaner to generate a single signature from this directive. Also: - Adds the symbol name, such that we don't depend on the location of this directive anymore. - Actually constructs the signature in the assembler, and make the assembler own it. - Refactor the use of MVT vs ValType in the streamer and assembler to require less conversions overall. - Changed 700 or so tests to use it. Reviewers: sbc100, dschuff Subscribers: jgravelle-google, eraman, aheejin, sunfish, jfb, llvm-commits Differential Revision: https://reviews.llvm.org/D54652 llvm-svn: 347228
2018-11-20 01:10:36 +08:00
; CHECK-NEXT: .functype i64_trunc_s_f64 (f64) -> (i64){{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; CHECK-NEXT: block
; CHECK-NEXT: f64.abs $push[[ABS:[0-9]+]]=, $0{{$}}
; CHECK-NEXT: f64.const $push[[LIMIT:[0-9]+]]=, 0x1p63{{$}}
; CHECK-NEXT: f64.lt $push[[LT:[0-9]+]]=, $pop[[ABS]], $pop[[LIMIT]]{{$}}
[WebAssembly] Fix fptoui lowering bounds To fully avoid trapping on wasm, fptoui needs a second check to ensure that the operand isn't below the supported range. llvm-svn: 319354
2017-11-30 04:20:11 +08:00
; CHECK-NEXT: br_if 0, $pop[[LT]]{{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; CHECK-NEXT: i64.const $push[[ALT:[0-9]+]]=, -9223372036854775808{{$}}
; CHECK-NEXT: return $pop[[ALT]]{{$}}
[WebAssembly] Fix fptoui lowering bounds To fully avoid trapping on wasm, fptoui needs a second check to ensure that the operand isn't below the supported range. llvm-svn: 319354
2017-11-30 04:20:11 +08:00
; CHECK-NEXT: BB
; CHECK-NEXT: end_block
; CHECK-NEXT: i64.trunc_s/f64 $push[[NUM:[0-9]+]]=, $0{{$}}
; CHECK-NEXT: return $pop[[NUM]]{{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
define i64 @i64_trunc_s_f64(double %x) {
%a = fptosi double %x to i64
ret i64 %a
}
; CHECK-LABEL: i64_trunc_u_f64:
[WebAssembly] replaced .param/.result by .functype Summary: This makes it easier/cleaner to generate a single signature from this directive. Also: - Adds the symbol name, such that we don't depend on the location of this directive anymore. - Actually constructs the signature in the assembler, and make the assembler own it. - Refactor the use of MVT vs ValType in the streamer and assembler to require less conversions overall. - Changed 700 or so tests to use it. Reviewers: sbc100, dschuff Subscribers: jgravelle-google, eraman, aheejin, sunfish, jfb, llvm-commits Differential Revision: https://reviews.llvm.org/D54652 llvm-svn: 347228
2018-11-20 01:10:36 +08:00
; CHECK-NEXT: .functype i64_trunc_u_f64 (f64) -> (i64){{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; CHECK-NEXT: block
; CHECK-NEXT: f64.const $push[[LIMIT:[0-9]+]]=, 0x1p64{{$}}
; CHECK-NEXT: f64.lt $push[[LT:[0-9]+]]=, $0, $pop[[LIMIT]]{{$}}
[WebAssembly] Fix fptoui lowering bounds To fully avoid trapping on wasm, fptoui needs a second check to ensure that the operand isn't below the supported range. llvm-svn: 319354
2017-11-30 04:20:11 +08:00
; CHECK-NEXT: f64.const $push[[ZERO:[0-9]+]]=, 0x0p0{{$}}
; CHECK-NEXT: f64.ge $push[[GE:[0-9]+]]=, $0, $pop[[ZERO]]{{$}}
; CHECK-NEXT: i32.and $push[[AND:[0-9]+]]=, $pop[[LT]], $pop[[GE]]{{$}}
; CHECK-NEXT: br_if 0, $pop[[AND]]{{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
; CHECK-NEXT: i64.const $push[[ALT:[0-9]+]]=, 0{{$}}
; CHECK-NEXT: return $pop[[ALT]]{{$}}
[WebAssembly] Fix fptoui lowering bounds To fully avoid trapping on wasm, fptoui needs a second check to ensure that the operand isn't below the supported range. llvm-svn: 319354
2017-11-30 04:20:11 +08:00
; CHECK-NEXT: BB
; CHECK-NEXT: end_block
; CHECK-NEXT: i64.trunc_u/f64 $push[[NUM:[0-9]+]]=, $0{{$}}
; CHECK-NEXT: return $pop[[NUM]]{{$}}
[WebAssembly] Fix trapping behavior in fptosi/fptoui. This adds code to protect WebAssembly's `trunc_s` family of opcodes from values outside their domain. Even though such conversions have full undefined behavior in C/C++, LLVM IR's `fptosi` and `fptoui` do not, and only return undef. This also implements the proposed non-trapping float-to-int conversion feature and uses that instead when available. llvm-svn: 319128
2017-11-28 09:13:40 +08:00
define i64 @i64_trunc_u_f64(double %x) {
%a = fptoui double %x to i64
ret i64 %a
}